Claude Code Extensions

A comprehensive collection of production-ready agents, hooks, commands, and output styles for Claude Code

Supercharge your Claude Code experience with 60+ specialized agents, 15 skills, 8 lifecycle hooks, 11 slash commands, and powerful automation tools—all ready to install and customize.

✨ Highlights

• 🤖 60+ Expert Agents - From code reviewers to deep research specialists (React, Django, Temporal, Cloudflare, Home Assistant, and more)
• 🎯 Model-Invoked Skills - Capabilities Claude discovers and uses automatically based on context
• 🔒 Safety-First Hooks - Block dangerous commands, protect sensitive files, audit all operations
• ⚡ Auto-Linting - Integrated Python, Go, and JS/TS linters that run automatically
• 🎯 Smart Orchestration - Tech-lead agents that coordinate multi-step tasks across specialists
• 📦 Easy Installation - Interactive CLI installer with settings.json merging
• 🧪 Battle-Tested - Production patterns from real-world Claude Code workflows

📦 Available Plugins

The repository provides 9 focused plugins (Phase 1) with 10+ more coming in future releases:

Plugin	Description	What's Included
cce-core	Essential foundation	13 agents (core, orchestrators, universal), 8 hooks, 2 skills, 8 commands
cce-kubernetes	Kubernetes operations	6 K8s health agents, 2 skills, 1 command
cce-cloudflare	Cloudflare development	5 Workers/AI/Workflows agents, 1 VPC skill
cce-esphome	ESPHome IoT	6 ESPHome agents, 2 skills (config, Box-3)
cce-web-react	React ecosystem	3 React/Next.js/TanStack agents
cce-django	Django backend	3 Django agents (backend, API, ORM)
cce-research	Deep research coordination	5 research agents (coordinator, academic, web, technical, data)
cce-grafana	Grafana observability	1 plugin expert agent, 2 skills (scaffolding, billing metrics)
cce-homeassistant	Home Assistant automation	7 HA experts (automation, integration, dashboard, add-on, API, voice, energy), 8 skills (incl. Frigate), 3 commands
cce-tauri	Tauri v2 desktop apps	1 Tauri v2 expert agent, 1 skill (IPC, capabilities, security)

Coming Soon: cce-web-vue, cce-temporal, cce-devops, cce-ai, cce-go, cce-python, cce-typescript, cce-anthropic

Install only what you need - no need to load 50+ agents if you only work with React!

🚀 Quick Start

Installation

Option 1: Plugin (Recommended for Multiple Projects)

Install as modular plugins via Claude Code's plugin system - pick only what you need for your tech stack:

# In any Claude Code session:
/plugin marketplace add github:nodnarbnitram/claude-code-extensions

Then install the plugins you need:

# Essential foundation (everyone needs this)
/plugin install cce-core@cce-marketplace

# Add plugins for your tech stack:
/plugin install cce-kubernetes@cce-marketplace    # For Kubernetes development
/plugin install cce-cloudflare@cce-marketplace    # For Cloudflare Workers/AI
/plugin install cce-esphome@cce-marketplace       # For ESPHome IoT
/plugin install cce-web-react@cce-marketplace     # For React/Next.js/TanStack
/plugin install cce-django@cce-marketplace        # For Django backend development
/plugin install cce-grafana@cce-marketplace       # For Grafana plugin development & billing
/plugin install cce-research@cce-marketplace      # For deep research tasks

Benefits:

• ✅ Modular - install only what you need
• ✅ Automatic updates across all projects
• ✅ Centralized management
• ✅ No repository cloning needed

Command namespaces:

• Core: /cce:git-commit, /cce:prime
• Kubernetes: /cce-kubernetes:health
• (Other plugins currently provide agents/skills only)

Option 2: Standalone (For Single Project or Custom Setup)

git clone https://github.com/nodnarbnitram/claude-code-extensions.git
cd claude-code-extensions
./install_extensions.py install ~/my-project

The installer lets you:

• ✅ Choose extensions interactively by type or category
• ✅ Preview changes with --dry-run before applying
• ✅ Merge settings.json safely without conflicts
• ✅ Copy dependencies automatically

# Common usage patterns
./install_extensions.py list                    # See all available extensions
./install_extensions.py info code-reviewer      # Get details on specific extension
./install_extensions.py install --dry-run ~/my-project   # Preview what will be installed
./install_extensions.py install --type agent --category core ~/my-project  # Install specific category

Option 3: Manual Copy

# Copy specific items manually
cp .claude/agents/core/code-reviewer.md ~/my-project/.claude/agents/
cp -r .claude/hooks ~/my-project/.claude/
cp .claude/settings.json ~/my-project/.claude/

Which Installation Method Should I Use?

Mode	Best For	Pros	Cons
Plugin	Multiple projects, team distribution	Auto-updates, centralized, modular	Namespaced commands
Standalone	Single project, custom setup	Full control, unprefixed commands	Manual updates, per-project install
Manual	Cherry-picking specific extensions	Maximum control	No automation, manual merging

Creating New Extensions

Agents - Use the built-in meta-agent:

> Use the meta-agent to create a [domain] specialist agent

Hooks - Use Python with uv script format (see CLAUDE.md for templates)

Commands - Create .md files in .claude/commands/ with frontmatter

Output Styles - Create .md files in .claude/output-styles/ with custom prompts

📖 Full guide: See CLAUDE.md for detailed patterns and examples

💡 Why Use This?

For Teams

• Share consistent workflows across your organization
• Enforce code quality standards automatically
• Onboard developers faster with specialized agents
• Version control your Claude Code configuration

For Solo Developers

• Automate repetitive tasks with hooks and commands
• Get expert-level assistance across multiple frameworks
• Keep your main Claude context focused with subagents
• Protect yourself from mistakes with safety hooks

For Learning

• Explore production-ready extension patterns
• Learn from 50+ agent examples across different domains
• Understand hook lifecycle and automation
• See how to structure complex AI workflows

📚 Extension Reference

Commands

Command	Description	Arguments
/agent-from-docs	Create a specialized agent by analyzing documentation URLs	<doc-url> [additional-urls...]
/prime	Load context for a new agent session by analyzing codebase structure, documentation and README	-
/git-status	Understand the current state of the git repository	-
/git-commit	Analyze changes and create well-formatted commits with emoji conventional format	[message] [--amend] (Optional)
/frontend-mode	Load Ultracite rules for JS/TS development	-
/security-scan	Run security scans on project files (Python/Go/JS/TS)	[path]
/wrapup-skillup	Generate session report capturing learnings, tools, pitfalls, and extension recommendations	[topic-slug]
/k8s-health	Run comprehensive Kubernetes cluster health diagnostics with dynamic operator discovery	[--operator <name>] [--output json|summary|detailed]
/ha-automation-lint	Validate Home Assistant automation YAML for syntax and best practices	[file-path]
/ha-blueprint-create	Convert a Home Assistant automation into a reusable blueprint	<automation-id-or-file>
/ha-integration-scaffold	Generate boilerplate for a new Home Assistant custom integration	<domain> [--with-config-flow] [--platforms ...]

Skills

Model-invoked capabilities that Claude automatically discovers and uses based on task context.

Skill	Description
commit-helper	Generate clear, conventional commit messages from git diffs
code-reviewer	Review code for best practices, security issues, and potential bugs (read-only)
kubernetes-operations	Kubernetes debugging, resource management, and cluster operations with token-efficient scripts
kubernetes-health	Comprehensive cluster health diagnostics using dynamic API discovery with operator-specific agents
grafana-plugin-scaffolding	Scaffold Grafana plugins (panel, data source, app, backend) with Docker dev environment
grafana-billing	Query Prometheus and Loki billing metrics from Grafana Cloud for cost analysis and optimization
ha-automation	Create and debug Home Assistant automations, scripts, blueprints, and Jinja2 templates
ha-integration	Develop custom Home Assistant integrations, config flows, entities, and platforms
ha-dashboard	Configure Home Assistant Lovelace dashboards, cards, views, and themes
ha-addon	Develop Home Assistant add-ons with Docker, Supervisor API, and multi-arch builds
ha-api	Integrate with Home Assistant REST and WebSocket APIs
ha-voice	Configure Home Assistant Assist voice control with pipelines, intents, and wake words
ha-energy	Set up Home Assistant energy monitoring with dashboards, solar, grid, and device tracking
tauri-v2	Tauri v2 cross-platform desktop/mobile app development with Rust backend, IPC patterns, and security configuration

Creating new skills:

• Use the skill-creator agent: > Use the skill-creator to create a skill for [purpose]
• Or copy the skeleton template: cp -r templates/skill-skeleton .claude/skills/my-skill

See docs/claude-code/agent-skills.md for detailed guidance.

Agents

📖 View All 50+ Agents (Meta, Core, Research, Orchestrators, Universal, Specialized)

Meta Agent

Agent	Description
meta-agent	Generates new, complete Claude Code sub-agent configuration files from descriptions using Opus

Core Agents

Agent	Description
code-reviewer	Rigorous, security-aware code review after features, bug-fixes, or pull-requests
code-archaeologist	Explores and documents unfamiliar, legacy, or complex codebases
fact-checker	Validates agent outputs to prevent hallucinations and ensure accuracy
documentation-specialist	Crafts and updates READMEs, API specs, architecture guides, and user manuals
performance-optimizer	Identifies bottlenecks and applies optimizations for high-performance systems

Research Agents

Agent	Description
research-coordinator	Plans and coordinates complex research tasks across specialists
academic-researcher	Searches scholarly sources, peer-reviewed papers with citation tracking
data-analyst	Quantitative analysis, statistical insights, data visualization
technical-researcher	Analyzes code repositories, technical docs, implementation details
web-researcher	Current news, industry reports, market trends, real-time intelligence

Orchestrators

Agent	Description
tech-lead-orchestrator	Strategic project analysis, coordinates multi-step tasks across sub-agents
project-analyst	Detects frameworks, tech stacks, architecture for proper routing
team-configurator	Sets up AI teams, selects specialists, updates CLAUDE.md config

Universal (Framework-Agnostic)

Agent	Description
api-architect	RESTful design, GraphQL schemas, OpenAPI specs
backend-developer	Server-side code across any language or stack
frontend-developer	Responsive UIs with React, Vue, Angular, Svelte, or vanilla JS
tailwind-css-expert	Tailwind CSS styling and utility-first refactors

Specialized: React

Agent	Description
react-component-architect	React 19+ patterns, hooks, component design
react-nextjs-expert	Next.js SSR, SSG, ISR, full-stack React
tanstack-start-expert	TanStack Start, Router, server functions

Specialized: Vue

Agent	Description
vue-component-architect	Vue 3 Composition API, composables
vue-nuxt-expert	Nuxt.js SSR, SSG, full-stack Vue

Specialized: Tauri

Agent	Description
tauri-v2-expert	Tauri v2 cross-platform desktop/mobile apps, Rust commands, IPC, security, Vite + TanStack Router

Specialized: Django

Agent	Description
django-backend-expert	Models, views, services, Django implementations
django-api-developer	DRF and GraphQL API development
django-orm-expert	ORM optimization, complex queries, migrations

Specialized: Python

Agent	Description
typer-expert	Typer CLI development, validation, testing

Specialized: Temporal.io

Agent	Description
temporal-core	Core concepts, architecture, determinism
temporal-python	Python SDK async/await, pytest, AsyncIO
temporal-go	Go SDK workflow-safe primitives, context
temporal-typescript	TypeScript SDK proxyActivities, type safety
temporal-testing	Testing strategies, time-skipping, mocking
temporal-troubleshooting	Error diagnosis, non-determinism issues

Specialized: Go

Agent	Description
go-google-style-expert	Google Go style guide, conventions, Go 1.25+

Specialized: Anthropic

Agent	Description
claude-agent-sdk-typescript-expert	Claude Agent SDK for TypeScript/Node.js
claude-agent-sdk-python-expert	Claude Agent SDK for Python

Specialized: Cloudflare

Agent	Description
cloudflare-workers-expert	Workers, edge computing, KV, D1, R2, Durable Objects
cloudflare-workers-ai-expert	Workers AI, model selection, RAG, streaming
cloudflare-workers-for-platforms-expert	Multi-tenant architectures, dispatch namespaces
cloudflare-workflows-expert	Durable execution, step APIs, DAG workflows
cloudflare-ai-agents-sdk-expert	AI Agents SDK, WebSockets, MCP servers

Specialized: Crossplane

Agent	Description
crossplane-upgrade-agent	Crossplane v1 to v2 migrations
crossplane-aws-rds-expert	AWS RDS provider, Aurora, compositions

Specialized: Kubernetes Health

Agent	Description
k8s-health-orchestrator	Orchestrates cluster health diagnostics, dispatches sub-agents based on API discovery
k8s-core-health-agent	Core Kubernetes health checks: nodes, pods, deployments, services, PVCs
k8s-crossplane-health-agent	Crossplane health: providers, compositions, claims, managed resources
k8s-argocd-health-agent	ArgoCD health: applications, sync status, app projects
k8s-certmanager-health-agent	Cert-manager health: certificates, issuers, expiry warnings
k8s-prometheus-health-agent	Prometheus health: instances, alertmanagers, service monitors

Specialized: Grafana

Agent	Description
grafana-plugin-expert	Grafana plugin development (panel, data source, app, backend), SDK patterns, React/Go

Specialized: Home Assistant

Agent	Description
ha-automation-expert	Automations, scripts, blueprints, Jinja2 templates
ha-integration-developer	Custom integrations, config flows, entities, platforms
ha-dashboard-expert	Lovelace dashboards, cards, views, themes
ha-addon-developer	Add-on development with Docker, Supervisor, S6 overlay
ha-api-expert	REST API, WebSocket API, authentication, service calls
ha-voice-expert	Assist pipelines, intents, wake words, voice satellites
ha-energy-expert	Energy dashboard, solar tracking, utility meters

Hooks

Python hooks using uv run --script for zero-config dependency management.

Hook	Event	Purpose
pre_tool_use.py	PreToolUse	🔒 Blocks dangerous commands, protects .env files, audit logging
post_tool_use.py	PostToolUse	📝 Logs executions, triggers auto-linting on file changes
session_start.py	SessionStart	🚀 Injects git status and project context
user_prompt_submit.py	UserPromptSubmit	📊 Logs and validates user prompts
pre_compact.py	PreCompact	💾 Preserves info before context compaction
stop.py	Stop	🏁 Runs when main agent finishes
subagent_stop.py	SubagentStop	🔄 Executes when subagent completes
notification.py	Notification	🔔 Handles Claude Code notifications
slack_notification.py	All events	💬 Sends Slack DMs for Claude Code events (requires SLACK_BOT_TOKEN, SLACK_USER_ID). Note: Caches transcript path on SessionStart to work around stale path bug in resumed sessions
lint/check.py	(Auto-triggered)	⚡ Auto-lints: ruff, golangci-lint, biome

Utilities: LLM integrations (Anthropic, OpenAI, Ollama), TTS engines (pyttsx3, OpenAI, ElevenLabs)

📖 Documentation

• CLAUDE.md - Complete guide for creating extensions
• CONTRIBUTING.md - How to contribute to this project
• docs/claude-code/ - Official Claude Code documentation

📋 Requirements

• Claude Code CLI
• uv - Python package manager
• Python 3.11+

🎯 Usage Examples

Auto Code Review

> Review my recent changes

The code-reviewer agent automatically analyzes your git diff.

Desktop Notifications Configure hooks for desktop alerts when Claude needs input (see CLAUDE.md).

Test Hooks Locally

echo '{"tool_name": "Bash", "tool_input": {"command": "ls"}}' > test.json
uv run ./.claude/hooks/pre_tool_use.py < test.json
echo $?  # 0 = allowed, 2 = blocked

🤝 Contributing

We welcome contributions! See CONTRIBUTING.md for:

• Development setup
• Testing guidelines
• Pull request process
• Style guidelines

Quick tips:

• Use the meta-agent to create new agents
• Follow existing patterns in .claude/hooks/
• Test thoroughly before submitting
• Update documentation with your changes

📦 Project Structure

.claude/
├── agents/           # 50+ specialized AI assistants
├── skills/           # Model-invoked capabilities
├── hooks/            # Lifecycle automation scripts
├── commands/         # Reusable slash commands
├── output-styles/    # Custom system prompts
└── settings.json     # Hook configuration

templates/
└── skill-skeleton/   # Starter template for new skills

docs/                 # Claude Code official docs
install_extensions.py # Interactive installer CLI

🔗 Resources

• Claude Code Docs
• Claude Code GitHub
• Report Issues

📄 License

MIT License - Free for everyone, including commercial use.

What this means:

• ✅ Use it anywhere - personal projects, startups, Fortune 500 companies
• ✅ Modify it however you want
• ✅ No permission needed
• ✅ Just keep the copyright notice

That's it. Use it, learn from it, build amazing things. 🚀